vertex-ai-fedramp-high-il2-launch

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.85). The skill’s required runtime workflow is to summarize and operationalize a specific vendor blog post (public web content) that is outsider-authored, and the LLM would ingest that fetched article text as readable prose via the “Source” URL path.